114 Photos and videos
FARR Conference Travel Support Applications Now Open
The FARR RCN connects researchers, cyberinfrastructure providers, policymakers, and industry partners to advance collaboration on AI Readiness, AI Reproducibility, and the intersection of FAIR Principles and Machine Learning. Progress in these areas depends on cross-disciplinary and multi-sector engagement. To facilitate this exchange, FARR is offering travel support for researchers attending PEARC26 or SC26 (Supercomputing 2026), so that they may seek out new and deepen existing collaborations that lead to future research and science impact.
We especially encourage applications from:
Early-career researchers
Students
Individuals who might otherwise be unable to participate
Support is available for eligible travel expenses in accordance with UC San Diego and federal funding guidelines.
Applications will be reviewed on a rolling basis through June 30, 2026. Apply here: forms.gle/4z75kidCYh76V5J27
Please share this opportunity with colleagues, students, and community members who may benefit from participating and building new collaborations within the FARR community.
35
You have got to be kidding....
news.slashdot.org/story/26/0โฆ
Here is the NY Times link (pay wall): nytimes.com/2026/06/01/climaโฆ
1
10
fils retweeted
๐The ESIP July Meeting agenda is now live!
Our sessions bring together the community for hands-on, interdisciplinary deep dives as we explore "Bridging Divides: Data, Technology, Community" this year.๐ก
2026julyesipmeeting.sched.coโฆ
1
2
49
OceanHackWeek 2026 (OHW26)
OceanHackWeek 2026 (OHW26) will be held on August 24-28, 2026 at the Bamfield Marine Sciences Centre on the West Coast of beautiful Vancouver Island, British Columbia, Canada.
oceanhackweek.org/ohw26/
1
33
fils retweeted
May 29
hot take: dynamic workflows is much better described as an instance of our DisCIPL framework, which predates both RLM and Opus 4.8 ๐๐
(arxiv v1 April 2025)
May 28
In case you're curious about why dynamic workflows are so powerful and the future, read the RLM paper! Opus 4.8 dynamic workflows in Claude Code is perhaps the first instance of a frontier model seriously trained to be an RLM.
I suspect within a year they'll just become the standard for nearly all coding agent interactions.
9
25
278
30,712
fils retweeted
May 28
DSPy v3.3.0 beta 1 is released on pypi! We would really appreciate your feedback!
We are introducing ReActV2 and a much improved LM/BaseLM system, along with a way to pass data to an RLM.
Thanks to @MaximeRivest, @kmad, and @mchonedev for their contributions.
Install it with `pip install dspy==3.3.0b1`
5
26
203
19,433
Recent agentic systems (Claude Code, Codex, RLM, etc.) push context out of the prompt and into the environment (e.g., as files). This helps them maintain long-term knowledge about their goals and functionality.
๐จ While this is a good idea, we show a surprising result: systems that use external environments like this perform much better when given a small, fixed-size, in-context, agent-managed cache that "๐ฑ๐ฆ๐ฆ๐ฌ๐ด ๐ช๐ฏ๐ต๐ฐ" these environments.
๐ Our paper, ๐ฃ๐๐๐: ๐ ๐จ๐ฎ๐จ๐ฉ๐๐ข ๐๐ค๐ง ๐๐ช๐๐ก๐๐๐ฃ๐ ๐๐ฃ๐ ๐ข๐๐๐ฃ๐ฉ๐๐๐ฃ๐๐ฃ๐ ๐ฎ๐ป ๐ผ๐ฟ๐ถ๐ฒ๐ป๐๐ฎ๐๐ถ๐ผ๐ป ๐ฐ๐ฎ๐ฐ๐ต๐ฒ ๐๐ค๐ง ๐๐๐ ๐๐๐๐ฃ๐ฉ๐จ, introduces this idea.
Compared with strong baselines, including RAG, Compaction Agents, and SOTA prompt-learning frameworks, PEEK dominates the costโquality Pareto frontier: achieving 6.3โ34.0% in quality, with fewer iterations and lower cost.
Paper: arxiv.org/abs/2605.19932
GitHub: github.com/zhuohangu/peek
More in the thread below! (1/N)
17
38
357
110,354
The ACM open access paper:
The (R)evolution of Scientific Workflows in the Agentic AI Era: Towards Autonomous Science
is a nice read. Some elements of section 3 are a bit deep for me. :) However, the rest is very easy to engage with. My workflow needs to rise to the level of ORNL, but much of what they talk about is broadly applicable.
dl.acm.org/doi/full/10.1145/โฆ
2
45
fils retweeted
The Builder Summer Cohort is enrolling now.
May 29 - Aug 21 | 4 micro-certificates | First one free
Built for data scientists, knowledge engineers, and technical practitioners. 12 weeks, live self-paced, includes a KGC 2027 virtual ticket.
1
1
5
186
fils retweeted
๐ The full CAIS '26 schedule is live.
61 peer-reviewed papers. 45 live system demos. Three keynotes. No pitch decks. No vibes-based benchmarks. No "AI-powered" anything without the receipts.
This is what it looks like when the field stops performing and starts publishing.
caisconf.org/schedule/2026/
We're nearly at our registration cap. Single-digit spots left.
caisconf.org/registration/
San Jose ยท May 26โ29
6
21
1,115
Will interesting to see the papers that come out of this.
An IEEE Agentic AI for Large-scale Science workshop.
Paper deadline July 13th.
agent4sc.github.io/
1
63
fils retweeted
May 15
Shell companies. Proxy owners. Fragmented registries.
On 6/4, Senzing Understand Beneficial Ownership break down #EntityResolution to find illicit finance โ #BeneficialOwnership, sanctions screening, PEP matching & more.
#GraphPowerHour w @pacoid
hubs.li/Q04gQ7Fw0
3
7
175
Job Opportunity:
Strategic Consultant, Open Science, Data Resilience (American Geophysical Union - AGU)
Enjoyed being a part of the related meeting in Berlin on this topic by AGU. Glad to see them make this position available to support the work.
paycomonline.net/v4/ats/web.โฆ
46
fils retweeted
May 12
Some awesome initial experiments on training small RLMs :)
A direction I think will be super super important moving forward for fully seeing the capabilities of RLMs vs. traditional agentic systems
May 12
Reinforcing Recursive Language Models
Can a 4B model learn to recursively call itself to answer hard long-context questions?
We RL fine-tuned a small model to behave as a native RLM.
On evidence selection across scientific papers, our 4B RLM matches Sonnet 4.6 in quality while running significantly faster and cheaper.
8
37
293
28,194
fils retweeted
May 11
how did I miss this! related to training RLMs :)
May 8
Sub-agents are a promising inference-time scaling primitive:
โข Expand an agent's working memory
โข Divide-and-conquer hard problems
โข Solve problems faster with parallel execution
But how do we train a model to best take advantage of sub-agents and make sure we get these benefits?
Very excited to release RAO: Recursive Agent Optimization.
RAO is an end-to-end reinforcement learning approach for training LLM agents to spawn, delegate to, and coordinate with recursive copies of themselves (that can themselves spawn other agents) - turning recursive inference into a learned capability.
1/10
5
17
346
50,161
Last Starfighter looses job to AI!
A tragic story, all too common today. The last Starfighter, High schooler Alex Rogan has lost his job to AI.
Read how Alex will be replaced as Google's DeepMind announces plan to train AI on player actions in quarter-million-player MMORPG Eve Online!
Is no job safe?!
tomshardware.com/tech-industโฆ
32
Hugging Face for Science at huggingscience.co/
This is very interesting. So I am exploring at what an agent optimized data repository looks like. So finding "Hugging Science" by Hugging Face was interesting. It is, so they say, a site optimized for your AI agent, and supports quite a few major domain specific data formats with large file support (huggingface.co/docs/datasetsโฆ). They have projects to get involved with, design challenges ( huggingscience.co/#/getting-โฆ ) etc. I don't see many geo-science datasets here yet. A call out to my community I guess.
Related paper: AI for scientific discovery is a social problem ( sciencedirect.com/science/arโฆ )
Is llms.txt still a thing?: huggingscience.co/llms.txt
1
87
